Loop issue with AutoGPT

[FlamingFury00]

Hello. The loop issue continues even after the updates. The model creates every single time another chat now. I will search for a solution myself, but in the meantime i will leave this issue open if someone knows how to solve this.

---

Ciao. Il problema del loop continua anche dopo gli aggiornamenti. Il modello crea ogni volta un'altra chat ora. Cercherò io stesso una soluzione, ma nel frattempo lascerò aperto questo issue se qualcuno sa come risolverlo.

[IntelligenzaArtificiale]

We have added the possibility to start from existing conversation .

from FreeLLM import ChatGPTAPI 

# Instantiate a ChatGPT object with your token
llm = ChatGPTAPI.ChatGPT((token="YOURTOKEN")  #for start new chat

# or if if u would to start from an existing chat 
# llm = ChatGPTAPI.ChatGPT(token = "YOUR-TOKEN", conversation = "Add-XXXX-XXXX-Convesation-ID")

# Generate a response based on the given prompt
response = llm("Hello, how are you?")

# Print the response
print(response)

We haven't tested it yet. But it would be enough to change this line in the AUTOGPT.py file:

# LINE 32 replace this llm= ChatGPTAPI.ChatGPT(token=os.environ["CHATGPT_TOKEN"]) with ->
llm = ChatGPTAPI.ChatGPT(token = "YOUR-TOKEN", conversation = "Add-XXXX-XXXX-Convesation-ID")

This way AutoGPT should always exchange messages in the same chat, even if it launches new instances of itself.

---

Facci sapre se cos' il loop è sistemato o se l'errore persite.

[FlamingFury00]

I saw this method in the README, but i didn't try that yet and i don't really like it. I feel like it's too "manual" if you know what I mean. I will find other ways and I'll let you know. I would like if it will be able to start a new chat and then associate the id automatically with that chat. If anyone else have some good option let us know.

---

Lascerò l'issue aperto per eventuali aggiornamenti :)